A system, method, and computer-readable medium for evaluating structural integrity of a gradient coil disposed in a magnetic resonance imaging system is provided. A sensor obtains a parameter reading of the gradient coil, wherein the parameter reading includes a back electromotive force (back emf) measurement. The structural integrity of the gradient coil is determined as function of the back emf measurement.
|
2. A method, comprising:
Obtaining via one or more sensors a parameter reading of a gradient coil disposed in a magnetic resonance imaging system, wherein the parameter reading includes a back electromotive force (back emf) measurement induced by movement of the gradient coil within a magnetic field provided by the magnetic resonance imaging system;
evaluating structural integrity of the gradient coil as a function of the back emf measurement;
retrieving a set of rules defining acceptance criteria for back emf measurements obtained from the gradient coil that are indicative of a structurally sound gradient coil; and
reporting a status of the structural integrity of the gradient coil to a system user.
1. A system, comprising:
a sensor operative to obtain a parameter reading of a gradient coil disposed in a magnetic resonance imaging system, wherein the parameter reading includes a back electromotive force (back emf) measurement induced by movement of the gradient coil within a magnetic field provided by the magnetic resonance imaging system; and
a controller configured to obtain the back emf measurement from the sensor and evaluate the structural integrity of the gradient coil as a function of the back emf measurement; and
a memory device storing a set of rules defining acceptance criteria for back emf measurements obtained from the gradient coil that are indicative of a structurally sound gradient coil;
wherein the controller is configured to report a status of the structural integrity of the gradient coil to a system user.
18. A non-transitory computer-readable medium having stored thereon executable instructions that, in response to execution, cause a system comprising at least one processor to perform operations directed to evaluating the structural integrity of a gradient coil disposed in a magnetic resonance imaging system, the operations comprising:
obtaining via one or more sensors a parameter reading of the gradient coil disposed in the magnetic resonance imaging system, wherein the parameter reading includes a back electromotive force (back emf) measurement induced by movement of the gradient coil within a magnetic field provided by the magnetic resonance imaging system;
evaluating the structural integrity of the gradient coil as a function of the back emf measurement;
retrieving a set of rules defining acceptance criteria for back emf measurements obtained from the gradient coil that are indicative of a structurally sound gradient coil; and
reporting a status of the structural integrity of the gradient coil to a system user.
3. The system of
4. The system of
5. The system of
6. The system of
7. The system of
8. The system of
9. The system of
10. The system of
11. The system of
12. The method of
13. The method of
14. The method of
15. The method of
16. The method of
17. The method of
|
The present patent application is a continuation-in-part of U.S. application Ser. No. 15/974,323, filed 8 May 2018, of which is hereby incorporated by reference in its entirety to provide continuity of disclosure.
This disclosure relates to a system, a method and a computer-readable medium for monitoring a health status of a gradient coil disposed in a magnetic resonance imaging system, and more particularly, to evaluating the structural integrity of the gradient coil.
Magnetic resonance imaging (“MRI”) is a widely accepted and commercially available technique for obtaining digitized visual images representing the internal structure of objects having substantial populations of atomic nuclei that are susceptible to nuclear magnetic resonance (“NMR”). Many MRI systems use superconductive magnets to scan a subject/patient via imposing a strong main magnetic field on the nuclei in the subject. The nuclei are excited by a radio frequency (“RF”) signal/pulse transmitted by a RF coil at characteristics NMR (Larmor) frequencies. By spatially disturbing localized magnetic fields surrounding the subject and analyzing the resulting RF responses, also referred to hereinafter as the “MR signal,” from the nuclei as the excited protons relax back to their lower energy normal state, a map or image of these nuclei responses as a function of their spatial location is generated and displayed. An image of the nuclei responses, also referred to hereinafter as an “MRI image” and/or simply “image,” provides a non-invasive view of a subject's internal structure.
Many MRI systems utilize large electromagnetic coils, commonly referred to as gradient coils, to generate magnetic gradient fields within a target volume containing the subject by exciting/energizing the gradient coils via an electrical current. Continued/repeated excitation of a gradient coil over an extended period of time, however, may damage the gradient coil, which in turn, may result in failure of the gradient coil, e.g., generation of degraded magnetic gradient fields and/or an inability to generate a magnetic gradient field at all. Typically, failure of a gradient coil results in unusable data from an MRI procedure/scan. As will be appreciated, many MRI procedures are often resource intensive. Thus, executing an MRI procedure/scan with an undetected failed gradient coil is often a costly event for both patients and MRI system operators, e.g., hospitals. Additionally, structural failure of the gradient coil may lead to increased sound pressure levels emitted by the gradient coil resulting in patient discomfort or, potentially, deleterious impacts on patient hearing.
Due to a variety of reasons, it is often difficult and/or impossible to predict when a particular gradient coil will fail via manual inspection. For example, gradient coils can be difficult to manually inspect as they are typically located/encased in a magnet assembly. As such, manual inspection of a gradient coil typically requires the MRI system to be taken offline, i.e., out of service, which reduces the availability of the MRI system to patients. Further, manual inspection of a gradient coil may not accurately predict failure of the gradient coil as many traditional gradient coil diagnostics systems are limited in their capabilities to detect/recognize symptoms indicative of an impending failure. While automated approaches for detecting a failed gradient coil exist, many such approaches are only effective after failure of the gradient coil has occurred. Additionally, such systems may be limited in their capabilities to detect/recognize symptoms indicative of an impending failure.
Thus, an improved system and method for monitoring a health status of a gradient coil disposed in an MRI system is generally desired.
In an embodiment, the present disclosure provides for a system for monitoring a health status of a gradient coil disposed in a magnetic resonance imaging system. The system includes one or more sensors and a controller. The one or more sensors are operative to obtain one or more parameter readings of the gradient coil, wherein the one or more parameter readings include at least one of an acoustic measurement and a back electromotive force measurement. The controller is in electronic communication with the one or more sensors and operative to generate the health status based on at least one of the acoustic measurement and the back electromotive force measurement.
In another embodiment, the present disclosure provides for a method for monitoring a health status of a gradient coil in a magnetic resonance imaging system. The method includes obtaining one or more parameter readings of the gradient coil via one or more sensors, wherein the one or more parameter readings include at least one of an acoustic measurement and a back electromotive force measurement. The method further includes generating, with a controller in electronic communication with the one or more sensors, the health status based on at least one of the acoustic measurement and the back electromotive force measurement.
In yet another embodiment, the present disclosure provides for a method of training a neural network. The method includes feeding a training dataset to the neural network. The training dataset includes a plurality of pairings each comprising of a parameter reading and a known health status of a gradient coil, wherein the parameter reading is at least one of an acoustic measurement and a back electromotive force measurement. The method further includes training the neural network in a supervised manner on the training dataset such that, for one or more of the pairings, the neural network generates a health status that substantially matches the known health status. The method further includes outputting, after the neural network has been trained, one or more weights of the neural network.
In yet another embodiment, the present disclosure provides for a system for monitoring a health status of a gradient coil. The system includes a sensor and a controller. The sensor is operative to obtain one or more parameter readings of the gradient coil. The controller is in electronic communication with the sensor and operative to generate the health status based at least in part on the one or more parameter readings.
Various aspects of this disclosure may be better understood upon reading the following detailed description and upon reference to the drawings in which:
The drawings illustrate specific aspects of the described systems and methods for monitoring a health status of a gradient coil. Together with the following description, the drawings demonstrate and explain the principles of the structures, methods, and principles described herein. In the drawings, the size of the components may be exaggerated or otherwise modified for clarity. Well-known structures, materials, or operations may not be shown or described in detail to avoid obscuring aspects of the described components, systems, and methods.
One or more specific embodiments of the present disclosure are described below in order to provide a thorough understanding. These described embodiments are only examples of systems and methods for monitoring a health status of a gradient coil. Moreover, as will be understood, embodiments of the invention are not limited to neural networks and, accordingly, may include other forms of artificial intelligence. The skilled artisan will understand that specific details described in the embodiments can be modified when being placed into practice without deviating from the spirit of the present disclosure.
When introducing elements of various embodiments of the present disclosure, the articles “a,” “an,” and “the” are intended to mean that there are one or more of the elements. The terms “first,” “second,” and the like, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. As the terms “connected to,” “coupled to,” etc. are used herein, one object (e.g., a material, element, structure, member, etc.) can be connected to or coupled to another object regardless of whether the one object is directly connected or coupled to the other object or whether there are one or more intervening objects between the one object and the other object. As used herein, “electrically coupled,” “electrically connected,” and “electrical communication” mean that the referenced elements are directly or indirectly connected such that an electrical current may flow from one to the other. The connection may include a direct conductive connection, i.e., without an intervening capacitive, inductive or active element, an inductive connection, a capacitive connection, and/or any other suitable electrical connection. Intervening components may be present.
In addition, it should be understood that references to “one embodiment” or “an embodiment” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Further, the limitations of the following claims are not written in means-plus-function format and are not intended to be interpreted as such, unless and until such claim limitations expressly use the phrase “means for” followed by a statement of function void of further structure.
Further, it is to be understood that embodiments of the present invention may be applicable to Positron Emission Tomography (“PET”)/MRIs and/or any other system having components susceptible to failure and/or degraded performance resulting from stresses incurred from use. For example, while the present invention is discussed herein as monitoring the health status of a gradient coil, it is to be understood that the systems and methods disclosed herein are equally applicable to other components in an MRI system, e.g., body coils, superconductive magnets, gradient amplifiers, etc.
Referring to the figures generally, the present disclosure is to provide systems and methods for monitoring a health status of a gradient coil disposed in an MRI system. In some embodiments, the systems and methods disclosed herein generate a health status of a gradient coil based on statistical deviation between one or more parameter readings of the gradient coil and the historical norms of the same parameters readings of gradient coils that have experienced little to no structural degradation. The term “parameter reading”, as used herein with respect to a gradient coil, refers to a measurement of a physical and/or chemical characteristic/metric of a gradient coil The parameter readings may be of various metrics of a gradient coil such as acoustics, e.g., sound waves, back electromotive force (“back EMF”) measurements, and/or other metrics related to the structural degradation of a gradient coil. As used herein, the terms “back electromotive force” and “back EMF” refer to a counter-electromotive force generated in a gradient coil after removal of an applied excitation current. The term “structural degradation”, as used herein with respect to a gradient coil, refers to changes in the physical and/or chemical structure of the materials forming the gradient coil.
In some embodiments, the controller may generate the health status based on a pre-determined/known correlation/scale/model that maps/correlates one or more statistical differences/variances of gradient coil parameter readings from historical norms to known levels/amounts of gradient coil structural degradation. In embodiments, the correlation between statistical deviations in parameter readings and structural degradation may be determined in part by passing parameter readings obtained from one or more gradient coils to a neural network, i.e., the neural network may be trained on a historical dataset of parameter readings acquired from the gradient coils of multiple MRI systems. By analyzing a dataset of historical parameter readings, the neural network of some embodiments is able to provide an accurate indication of the health status of a gradient coil based on new parameter readings acquired from the gradient coil. Thus, in some embodiments, the controller may generate a health status for a gradient coil by passing/feeding parameter readings acquired from the gradient coil to a neural network. Additionally, in some embodiments, the controller and/or neural network is able to predict a time period during which the gradient coil may be expected to fail.
Now referring to
In embodiments, the MRI system control 32 includes a set of modules connected together by a backplane 38. These include a CPU module 40 and a pulse generator module 42, which connects to the operator console 12 through a serial link 44. It is through link 44 that the system control 32 receives commands from the operator to indicate the scan sequence that is to be performed. The pulse generator module 42 operates the system components to execute the desired scan sequence and produces data which indicates the timing, strength and shape of the RF pulses produced, and the timing and length of the data acquisition window. The pulse generator module 42 connects to a set of gradient amplifiers 46, to indicate the timing and shape of the gradient pulses that are produced during the scan. The pulse generator module 42 can also receive patient data from a physiological acquisition controller 48 that receives signals from a number of different sensors connected to the patient, such as ECG signals from electrodes attached to the patient. And finally, the pulse generator module 42 connects to a scan room interface circuit 50, which receives signals from various sensors associated with the condition of the patient and the magnet system. It is also through the scan room interface circuit 50 that a patient positioning system 52 receives commands to move the patient to the desired position for the scan.
The pulse generator module 42 operates the gradient amplifiers 46 to achieve desired timing and shape of the gradient pulses that are produced during the scan. The gradient waveforms produced by the pulse generator module 42 are applied to the gradient amplifier system 46 having Gx, Gy, and Gz amplifiers. Each gradient amplifier excites a corresponding physical gradient coil in a gradient coil assembly, generally designated 54, to produce the magnetic field gradients used for spatially encoding acquired signals. The gradient coil assembly 54 forms part of a magnet assembly 56, which also includes a polarizing magnet 58 (which in operation, provides a homogenous longitudinal magnetic field B0 throughout a target volume 60 that is enclosed by the magnet assembly 56) and a whole-body (transmit and receive) RF coil 62 (which, in operation, provides a transverse magnetic field B1 that is generally perpendicular to B0 throughout the target volume 60).
The resulting signals emitted by the excited nuclei in the patient may be sensed by the same RF coil 62 and coupled through the transmit/receive switch 64 to a preamplifier 66. The amplifier MR signals are demodulated, filtered, and digitized in the receiver section of a transceiver 68. The transmit/receive switch 64 is controlled by a signal from the pulse generator module 42 to electrically connect an RF amplifier 70 to the RF coil 62 during the transmit mode and to connect the preamplifier 66 to the RF coil 62 during the receive mode. The transmit/receive switch 64 can also enable a separate RF coil (for example, a surface coil) to be used in either transmit or receive mode.
The MR signals picked up by the RF coil 62 are digitized by the transceiver module 68 and transferred to a memory module 72 in the system control 32. A scan is complete when an array of raw K-Space data has been acquired in the memory module 72. This raw K-Space data/datum is rearranged into separate K-Space data arrays for each image to be reconstructed, and each of these is input to an array processor 76 which operates to Fourier transform the data into an array of image data. This image data is conveyed through the serial link 34 to the computer system 22 where it is stored in memory 30. In response to commands received from the operator console 12, this image data may be archived in long-term storage or it may be further processed by the image processor 26, conveyed to the operator console 12, and presented on the display 18.
As illustrated in
Illustrated in
Turning to
The controller 106 is in electronic communication with the one or more sensors 98, 100, 102, the memory device 104, and is operative/configured/adapted to generate a health status 110 (
As best seen in
For example, in certain embodiments, one or more of the sensors 98, 100, 102 may be a microphone, e.g., a condenser or optical microphone, that acquires acoustic measurements which may be of frequency, amplitude, or other sound-based metrics, generated by the gradient coil 86, 88, and/or 90. As will be understood, the acoustics of a gradient coil 86, 88, and/or 90 change as the level/amount of structural degradation of the coil 86, 88, and/or 90 changes. Thus, by mapping acoustics sampled from a gradient coil 86, 88, and/or 90 to known levels of structural degradation, embodiments of the present invention create a model, e.g., a neural network, that can be used to find the structural degradation of other gradient coils based on their acoustics.
Referring now to
As illustrated in
Accordingly,
Thus, in embodiments, the one or more sensors 98, 100, 102 may include a voltmeter that measures the back EMF voltage 202 in a gradient coil 86, 88, and/or 90. As will be appreciated, in embodiments, the voltmeter 98, 100, 102 may be disposed in one or more of the x, y, or z gradient amplifiers 46 as further shown in
While the foregoing paragraphs have discussed the one or more parameter readings 107 (
Moving now to
As shown in
where n is the total number of input connections 130 to the neuron 112. In embodiments, the value of Y may be based at least in part on whether the summation of WiXi exceeds a threshold. For example, Y may have a value of zero (0) if the summation of the weighted inputs fails to exceed a desired threshold.
As will be further understood, the input connections 130 of neurons 112 in the input layer 114 (
For example, as shown in
Turning to
The method 146 may further include determining, at step 151, whether the generated health status 110 has exceeded a threshold 154 (
In embodiments, the method 146 may further include preventing, at step 160, via the controller 106 (
Embodiments of the present invention may also provide for methods of training the neural network 108 (
While the above paragraphs discuss training the neural network 108 via supervised methods, as will be appreciated, other methods of training the neural network 108 may be employed, e.g., unsupervised learning. As used herein, the term “unsupervised learning” refers to a process of training the weights of the neural network 108 without known outputs. For example, in such embodiments, the neural network 108 may be configured to train the weights so as to maximize a cost function.
Moving to
For example, parameter readings 107 (
As will be appreciated, as new/younger MRI systems, e.g., MRI system 172, come online after the neural network 108 has had the opportunity to be trained on parameter readings 107 (
As will be understood, in such embodiments, the neural network 108 may generate progressively lower scores corresponding to the amount that the parameter readings 107 of the gradient coil 166 in the new/younger MRI system 172 deviate from the historical norms, with zero (0) being the maximum amount of detectable deviation. In other words, in such embodiments, a health status/score 110 (
Additionally, in embodiments, the neural network 108 may provide for a correlation between gradient coil acceleration, i.e., physical vibrations, and/or acoustics, and gradient coil failure; and similarly, for a correlation between inductance-and-resistance (“LR”) and back EMF and gradient coil failure.
As will be appreciated, while the above described training scenario concerned parameter readings 107 (
Referring back to
The use of a neural network to monitor the health status of the gradient coils 86, 88, and/or 90 is representative of one approach that can be deployed by the system 96 depicted in
In one embodiment, the parameter readings 107 obtained from one or more of the coils 86, 88, 90 by the sensors 98, 100, 102 includes a back EMF measurement as discussed above with regard to
In one embodiment, the controller 106 of the system 96 depicted in
The operations of the flow chart 400 begin by applying and removing an excitation current to the gradient coils 86, 88, and 90. In particular, as shown in operation 402 of
The sensors 98, 100, 102 can obtain the back EMF measurements, which as noted above can alternatively be referred to as back EMF voltage measurements, over the full range of frequencies and provide the measurements to the controller 106 for evaluation. With reference to the flow chart 400 of
At 406, the controller 106 evaluates the back EMF voltage measurements from each of the gradient coils against a predetermined set of rules containing acceptance criteria that relates to gradient coil structural integrity. The acceptance criteria, which is explained below in more detail, specifies predefined requirements for the amplitudes of the back EMF measurements for each of the frequencies that were measured. In an embodiment, the acceptance criteria is established from a population or a plurality of gradient coils having structural integrity deemed sound and intact. In general, this acceptance criteria is derived from back EMF measurements obtained from the population of gradient coils over the full range of frequencies that are tested and measured in the flow chart 400.
If the controller 106 determines at 408 that any of the back EMF voltage measurements obtained from the gradient coils 86, 88, and 90 at any of the frequencies fails to satisfy the acceptance criteria, then the corresponding coil with the violation of the acceptance criteria is identified at 410. Alternatively, if the controller 106 determines at 408 that the back EMF voltage measurements obtained from the gradient coils 86, 88, and 90 at all of the frequencies satisfy the acceptance criteria, then each of the coils is identified at 412 as having acceptable structural integrity (i.e., the coils are deemed structurally sound and intact). In general, a single failure of any one of the gradient coils 86, 88, and 90 at one of the frequencies is indicative of a complete failure of a coil. However, it is understood that if there is only a minimal amount of failures for a gradient coil over the range of frequencies, then it may be possible to make a refinement to the coil in order to avoid discarding the coil. Those skilled in the art will appreciate that the extent of the failures and the degree to the amount of violation between the back EMF measurements and acceptance criteria are some of the factors that can determine whether refinement of the gradient coil is a suitable option as opposed to discarding the coil.
While for purposes of simplicity of explanation, the operations shown in
Although the above paragraphs discuss the evaluation of the structural integrity of the gradient coils as a computer-implemented process, it is understood that not all aspects of this evaluation should be limited to the use of a computer system to facilitate the evaluation described in the various embodiments. For example, the decision of whether the gradient coils have sound or intact structural integrity can include a person evaluating the data as opposed to a computer system.
As noted previously, the acceptance criteria can be established from back EMF measurements obtained from a population of gradient coils deemed to have acceptable structural integrity that is solid and intact. Generally, a population of at least 10 to 20 gradient coils should be a sufficient number of coils to obtain back EMF measurements that can be used to derive the acceptance criteria. These back EMF measurements are generally collected over a full range of frequencies that could be used to test the gradient coils. In addition to collecting the back EMF measurements over the full range of frequencies, these measurements can also be classified according to the type of gradient coil (i.e., x-gradient coil, y-gradient coil, and z-gradient coil).
The application of the gradient waveforms to each of the gradient coils in a population of coils over a range of frequencies, collection of back EMF measurements from the coils, compilation of the results, and derivation of the acceptance criteria from the results for each of the frequencies are functions that those skilled in the art can perform using any of a number of well-known data collection and analyzation techniques familiar to those skilled in collecting and analyzing data from MRI systems. For example, the acceptance criteria can be established by developing a statistical distribution from the back EMF measurements obtained from the population of structurally sound or intact gradient coils. Based on the statistical distribution of the back EMF measurements from the population of structurally sound or intact gradient coils, the acceptance criteria can then be set based on the values of the back EMF measurements. For example, the failure limit could be set at a mean value from a set of known good gradient back-EMF measurements plus 1-3 standard deviations for each of the frequencies.
After the acceptance criteria has been established, then the rules can be stored in the memory device 104 of the system 96 depicted in
In one embodiment, the acceptance criteria that is established excludes back EMF measurements that correspond with regions near mechanical resonance frequencies of the gradient coil. As used herein, regions near mechanical resonance frequencies means within several bandwidths of the resonance frequency where the mechanical resonance bandwidth is defined by the full width half maximum of the mechanical resonance.
It has been determined that excluding regions near mechanical resonance frequencies can make the structural integrity evaluation more robust because there is more variability associated with the measurements around these regions of mechanical resonance frequencies due to factors that can include, but are not limited to the magnet type deployed in the MRI system and the mounting of the gradient coils. This variability in the measurements around these regions of mechanical resonance frequencies makes it more likely that the structural integrity evaluation can have “false positives”, i.e., that is identify a structurally sound coil as one that is structurally compromised or degraded. By excluding the mechanical resonance frequencies from the acceptance criteria, and focusing on regions that are more stable, any instances of measurements that violate the criteria are considered better indicators of a compromised or degraded gradient coil because the variability of the mechanical resonance frequencies has been removed from the evaluation. Accordingly, by focusing on frequencies in regions that are between the mechanical resonance resonances, then there will be greater specificity with the back EMF measurements, which obviates the structural integrity evaluation having “false positives” which could lead to the needless removal of structurally sound gradient coils. In addition, removing the regions of mechanical resonance resonances from the acceptance criteria not only improves the specificity of the back EMF measurements, but also increases the repeatability of the measurements which further reducing the risk of the evaluation having “false positives.”
In an embodiment in which mechanical resonance frequencies are excluded, the acceptance criteria can comprise a single rule. For example, the acceptance criteria in this embodiment can include a peak back EMF voltage upper specification limit that is less than or equal to a mean plus a predetermined standard deviation of peak back EMF voltage measurements obtained from the population or plurality of known gradient coils with acceptable structural integrity. The predetermined standard deviation used with this acceptance criteria can include but is not limited to 3, 5 and 7 standard deviation. However, it is understood that other standards of deviation can be utilized, and thus the embodiments of the present invention should not be limited to any particular standard of deviation.
In this particular example 500, the evaluated gradient coil represented by the line 514 fails to meet the acceptance criteria represented by line 510, which would likely be interpreted by a human observer, as “good” coil, i.e., a coil with structural integrity that is sound or intact. On the other hand, the acceptance criteria represented by line 512, which excludes the mechanical resonance frequencies would identify the gradient coils as a compromised or degraded coil due to the measurements associated with the evaluated coil violating the acceptance criteria of line 512. In this example, the acceptance criteria represented by line 512 that excludes the mechanical resonance frequencies would include frequency points in the following ranges: 100 Hz to 300 Hz, 435 Hz to 518 Hz, and 635 Hz to 900 Hz. The acceptance criteria that is used to evaluate the gradient coil for structural integrity is a Vpp upper specification limit the mean+7*standard deviation of measurements from known good coils.
Since the evaluation approach that excludes the mechanical resonance frequencies does not utilize all of the available data in the assessment of gradient coil health (i.e., the structural integrity), it may be desirable to provide specific acceptance criteria that utilizes back EMF measurements in regions that include mechanical resonance frequencies and regions that are between the mechanical resonance frequencies in order to improve sensitivity of the evaluation. Accordingly, in one embodiment, the acceptance criteria comprises predefined requirements for back EMF measurements that correspond with regions of mechanical resonance frequencies of the gradient coil and regions of back EMF measurements that correspond with other frequencies between the mechanical resonance frequencies. In this embodiment, the predefined requirements for the regions of mechanical resonance frequencies can have a more lenient acceptance criteria to account for the variability that is associated with these regions.
For example, the predefined requirement for back EMF measurements that corresponds with regions of mechanical resonance frequencies can comprises a peak back EMF voltage upper specification limit that is equal to a predetermined variability mitigation multiplier applied to a mean plus a predetermined standard deviation of peak back EMF voltage measurements obtained from a plurality of known gradient coils with acceptable structural integrity. The variability mitigation multiplier in this specification limit provides an extra cushion (e.g., 10%) to account for the variation in the mechanical resonance frequencies. In addition, the predetermined standard deviation that is utilized can be increased to provide further leeway in order to account for the regions of mechanical resonance frequencies.
The predefined requirement for back EMF measurements that corresponds with frequencies between the mechanical resonance frequencies can comprise acceptance criteria like that discussed above. For example, the predefined requirement for the regions between the mechanical resonance frequencies can comprise a peak back EMF voltage upper specification limit that is equal to a mean plus a predetermined standard deviation of peak back EMF voltage measurements obtained from a plurality of known gradient coils with acceptable structural integrity.
The benefits to the aforementioned rule-based approach for evaluating the structural integrity of the gradient should be apparent from the various embodiments described herein. In particular, these embodiments provide solutions to the technical problem of evaluating the structural integrity of a gradient coil utilized in an MRI system that include providing savings in terms of time and costs in evaluating a coil. The savings in terms of time and costs that can be realized with the automated approach for evaluating the structural integrity of a gradient coil as described in these embodiment can be realized in remote monitoring and diagnostics of the coil by obviating the need to send a technician to the site of the MRI system to determine the health of the coil. Furthermore, this structural integrity evaluation can be utilized during production of the MRI system to ensure that the system is installed with gradient coils that are not structurally degraded or compromised.
Finally, it is also to be understood that the systems 10 and/or 96 may include the necessary electronics, software, memory, storage, databases, firmware, logic/state machines, microprocessors, communication links, displays or other visual or audio user interfaces, printing devices, and any other input/output interfaces to perform the functions described herein and/or to achieve the results described herein. For example, as previously mentioned, the systems 10 and/or 96 may include at least one processor and system memory/data storage structures, which may include random access memory (RAM) and read-only memory (ROM). The at least one processor of the systems 10 and/or 96 may include one or more conventional microprocessors and one or more supplementary co-processors such as math co-processors or the like. The data storage structures discussed herein may include an appropriate combination of magnetic, optical and/or semiconductor memory, and may include, for example, RAM, ROM, flash drive, an optical disc such as a compact disc and/or a hard disk or drive.
Additionally, a software application that adapts a controller to perform the methods disclosed herein may be read into a main memory of the at least one processor from a computer readable medium, e.g., a medium that provides or participates in providing instructions to the at least one processor of the systems 10 and/or 96 (or any other processor of a device described herein) for execution. Such a medium may take many forms, including but not limited to, non-volatile media and volatile media.
While in embodiments, the execution of sequences of instructions in the software application causes at least one processor to perform the methods/processes described herein, hard-wired circuitry may be used in place of, or in combination with, software instructions for implementation of the methods/processes of the present invention. Therefore, embodiments of the present invention are not limited to any specific combination of hardware and/or software.
It is further to be understood that the above description is intended to be illustrative, and not restrictive. For example, the above-described embodiments (and/or aspects thereof) may be used in combination with each other. Additionally, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from its scope.
Accordingly, by providing automated monitoring of a health status of a gradient coil, some embodiments of the present invention may reduce the risk of the gradient coil failing during an MRI scan without the need to manually inspect the gradient coil. As will be appreciated, such embodiments may improve the patient throughput of an MRI system by avoiding the need to rescan a patient due to a failed gradient coil, as well as reducing and/or avoiding down time of an MRI system incurred during manual inspection of the gradient coils.
Further, by predicting a time period during which a gradient coil is expected to fail, some embodiments of the present invention may provide for improved patient throughput over traditional MRI systems by facilitating improved coordination between scheduling patient scans and MRI system down time due to gradient coil maintenance/replacement. In other words, some embodiments of the present invention provide for proactive maintenance of gradient coils, as opposed reactively detecting an already failed gradient coil. In such embodiments, proactive maintenance of gradient coils may improve patient safety/comfort by reducing the risk that a patient will be exposed to excessive gradient coil noise/vibrations.
Further still, by using the gradient amplifiers of an MRI system to obtain back EMF parameter readings, some embodiments of the present invention provide for a system of monitoring the health status of a gradient coil that makes use of existing sensors/equipment presently found in many MRI systems. Thus, such embodiments of the present invention provide for improved monitoring of the health status of a gradient coil without incurring the significant costs typically associated with developing and/or installing new types of sensors into existing MRI systems already in use at various locations.
Yet further still, by storing and analyzing historical dataset/parameter readings, of gradient coils in multiple MRI systems, in a server, some embodiments of the invention may provide for improved understanding of future gradient coil failures. For example, in such embodiments, analysis of the historical data of the acceleration history of a failed gradient coil by the neural network may facilitate faster identification of the root cause of the failure.
In addition to any previously indicated modification, numerous other variations and alternative arrangements may be devised by those skilled in the art without departing from the spirit and scope of this invention, and the appended claims are intended to cover such modifications and arrangements. Thus, while the invention has been described above with particularity and detail in connection with what is presently deemed to be the most practical and preferred aspects, it will be apparent to those of ordinary skill in the art that numerous modifications, including, but not limited to, form, function, manner of operations, and/or use may be made without departing from the principles and concepts set forth herein.
Finally, the examples and embodiments used herein are meant to be illustrative only and should not be construed to be limiting in any manner.
Seeber, Derek, Panos, Andrew John, Astary, Garrett William
Patent | Priority | Assignee | Title |
Patent | Priority | Assignee | Title |
8373417, | Jun 05 2009 | Siemens Healthcare GmbH | Method and device to detect failure of a magnetic resonance gradient coil by monitoring a supply cable thereof |
8373471, | Aug 18 2010 | SK Hynix Inc. | Semiconductor apparatus and DLL circuit using the same |
20030215125, | |||
20050156596, | |||
20110184250, | |||
20130303870, | |||
20150369888, | |||
20160178713, | |||
20160327606, | |||
20160328852, | |||
20170059670, | |||
20170146677, | |||
20170307702, | |||
20170336483, | |||
CN104237818, | |||
WO2017018755, |
Executed on | Assignor | Assignee | Conveyance | Frame | Reel | Doc |
Jan 25 2022 | ASTARY, GARRETT WILLIAM | GE Precision Healthcare LLC | ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS | 058809 | /0137 | |
Jan 25 2022 | SEEBER, DEREK | GE Precision Healthcare LLC | ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS | 058809 | /0137 | |
Jan 26 2022 | PANOS, ANDREW JOHN | GE Precision Healthcare LLC | ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS | 058809 | /0137 | |
Jan 28 2022 | GE Precision Healthcare LLC | (assignment on the face of the patent) | / |
Date | Maintenance Fee Events |
Jan 28 2022 | BIG: Entity status set to Undiscounted (note the period is included in the code). |
Date | Maintenance Schedule |
Mar 26 2027 | 4 years fee payment window open |
Sep 26 2027 | 6 months grace period start (w surcharge) |
Mar 26 2028 | patent expiry (for year 4) |
Mar 26 2030 | 2 years to revive unintentionally abandoned end. (for year 4) |
Mar 26 2031 | 8 years fee payment window open |
Sep 26 2031 | 6 months grace period start (w surcharge) |
Mar 26 2032 | patent expiry (for year 8) |
Mar 26 2034 | 2 years to revive unintentionally abandoned end. (for year 8) |
Mar 26 2035 | 12 years fee payment window open |
Sep 26 2035 | 6 months grace period start (w surcharge) |
Mar 26 2036 | patent expiry (for year 12) |
Mar 26 2038 | 2 years to revive unintentionally abandoned end. (for year 12) |